Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to temporal phrases indicating duration or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    subsubsection
    -0.52
     dintre
    -0.46
    ║
    -0.46
     dedans
    -0.45
     Handbuch
    -0.44
     an
    -0.44
    utica
    -0.44
    ınca
    -0.44
    ъ
    -0.43
     LIABLE
    -0.43
    POSITIVE LOGITS
     last
    1.10
     scorso
    1.05
    awtextra
    1.02
     afgelopen
    1.02
     sidste
    0.99
     últimos
    0.97
     posled
    0.96
    BagLayout
    0.90
     BoxFit
    0.90
     past
    0.89
    Act Density 0.098%

    No Known Activations